code-ingest
Skill35 starsChanged 2 months agoMITView on GitHub
Adds a code repository to the Obsidian code library with its purpose, usage, and links to research projects. Use when the user hands over a repo URL or path and says 'add to the code library', 'разбери репозиторий', or starts a project that uses a repo missing from Code/.
1 other project uses a version of this.
Adopted by
Most recently taken up by
- shkodnik1917/claude-brainlabword for word, first seen Nov 8, 2026
Other versions1 project uses a version of this.
Word for word · 1
- shkodnik1917/claude-brainlab★ 35100% same
Edited · 0
None found.
Wrote their own version · 0
None found.
How matches are found. Word for word: the exact same text. Edited: shares passages with this file (“99% same” means 99% of its five-word phrases also appear here; 10% or more counts). Their own version: similar meaning, or, weakest, the same name. We can’t tell which project had it first. Projects are counted among the 200 most-starred candidates, and mentions are links to the repository we found, up to 50 per site, so both counts are a floor.
In this repository68 other files it gives its agents.
- rules/agents.mdAGENTS.md
- CLAUDE.mdCLAUDE.md
- academic-plottingSkill
- agent-identifierSkill
- architecture-designSkill
- astar-paper-reviewSkill
- bug-detectiveSkill
- call-notesSkill
- cavemanSkill
- citation-verificationSkill
- code-librarySkill
- code-review-excellenceSkill
- command-developmentSkill
- create-projectSkill
- daily-codingSkill
- defuddleSkill
- diagnoseSkill
- doc-coauthoringSkill
- experiment-runsSkill
- frontend-designSkill
- git-guardrails-claude-codeSkill
- git-workflowSkill
- google-workspace-mcpSkill
- grill-meSkill
- grill-with-docsSkill
- handoffSkill
- handoff-to-jarvisSkill
- hook-developmentSkill
- improve-codebase-architectureSkill
- json-canvasSkill
- kaggle-learnerSkill
- lab-knowledgeSkill
- latex-conference-template-organizerSkill
- mcp-integrationSkill
- ml-paper-writingSkill
- obsidian-basesSkill
- obsidian-cliSkill
- obsidian-experiment-logSkill
- obsidian-markdownSkill
- operon-obsidian-setupSkill
- paper-ingestSkill
- paper-searchSkill
- paper-to-socialSkill
- paper-venue-formattingSkill
- pdf-readerSkill
- planning-with-filesSkill
- plugin-structureSkill
- presentationSkill
- presenter-modeSkill
- prototypeSkill
- research-cycleSkill
- research-ideationSkill
- restore-sessionSkill
- results-analysisSkill
- results-reportSkill
- reverse-outline-flow-checkSkill
- review-responseSkill
- setup-pre-commitSkill
- skill-developmentSkill
- tddSkill
- The first 60 shown.
The file
We split this skill into the rules it gives an agent
6 rules. About 0 are common, 3 are distinctive, and 3 are very specific to this project.
≈0
Common · estimate
Many files like this have a rule of this kind.
≈3
Distinctive · estimate
This author's own choices. Worth a look.
3
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Distinctive: line 17
Before heavily editing an unfamiliar repo (build the map first).
- Very specific: line 37
Update Code/README.md (the library index) with a one-line entry for the new repo.
- Very specific: line 40
Get the source: Prefer reading a local clone or the server copy if one exists (ask / check the project card).
- Distinctive: line 105
Keep each note focused; 200-400 lines max, split if larger.
- Distinctive: line 107
Use Obsidian wikilinks between the overview and module notes.
- Very specific: line 108
After ingesting, remind the user to add a ## Код section to the relevant project hub card (see [[code-library]]).
≈ “Common” is an estimate: at least 1 in 5 of the 350,495 skill files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.
Files
code-ingest — add a repository to the Obsidian Code library
Turns a repo into a map you can read in 2 minutes and instantly recall how the code is organized and where to look to change something — without duplicating the source. The code itself stays in git / on the server; these notes are the index.
When to use
- The user hands you a repo URL or path and says "add to the code library" / "разбери репо".
- A project starts depending on external code that has no
Code/<repo>/folder yet. - Before heavily editing an unfamiliar repo (build the map first).
When NOT to use
- The repo is already in
Code/<repo>/and unchanged → just read it. Re-run only to refresh after large upstream changes. - For per-project edits/diffs → those go in the project hub card
## Кодsection, not here (see [[code-library]]).
Where it lives
Vault (the lab tree): ${OBSIDIAN_VAULT}/personal/code-library/
One folder per repo: personal/code-library/<repo-slug>/. The slug is the repo name, kebab-case.
Output structure (always)
Code/<repo>/
<repo>.md ← CANONICAL OVERVIEW. Always this exact name. Read this first.
architecture.md ← entrypoint, control/data flow, how a run executes end-to-end
<module>.md ← one note per major module/package (group tiny files)
...- The overview
<repo>.mdis mandatory and always named after the folder, so any agent knows which file to open first. - Split into module notes when the repo is large; for a tiny repo a single
<repo>.mdis fine. - Update
Code/README.md(the library index) with a one-line entry for the new repo.
Procedure
- Get the source. Prefer reading a local clone or the server copy if one exists (ask / check the project card). Otherwise fetch file listing + key files from GitHub (raw URLs /
gh). Note the canonical git URL and default branch. - Map the layout. List top-level dirs and the role of each. Identify: entrypoint(s), config system, the main loop, the factory/registry or dispatch points (where names map to classes), data path, outputs/checkpoints.
- Trace one full run end-to-end (what
maindoes, in order) — this becomesarchitecture.md. - Write module notes using the template below. For each module: what it's for, key files with GitHub permalinks and line anchors, key classes/functions, and an explicit "where to edit to change X" list. Do not paste code bodies — cite
path:line+ a one-line description. - Write the overview
<repo>.mdusing its template. - Index it in
Code/README.md. - Tell the user what was created and link the overview.
Overview template (<repo>.md)
---
tags: [code, <repo-slug>]
repo: <git url>
default_branch: <branch>
created: DD-MM-YYYY
---
# <repo> — code map
One-paragraph: what this repo is and what you use it for.
## At a glance
- **Entrypoint:** `path` (`func`)
- **Config:** how runs are parametrized (flags / yaml / hydra)
- **Run a job:** the minimal command
- **Data:** where data lives / how it's loaded
- **Outputs:** where checkpoints / logs / metrics go
- **Dispatch points:** where a name (optimizer/model/dataset) maps to a class
## Directory map
| path | role | note |
|------|------|------|
| ... | ... | [[architecture]] / [[<module>]] |
## Where to look to change X
- change the model arch → [[models]] (`...`)
- add an optimizer → [[optimizers]] (`...`)
- change the schedule → ...
- change data → ...
## Notes
- [[architecture]] · [[optimizers]] · [[models]] · [[data]] · ...
## Used by projects
- [[<направление>/<тема>/<работа>/README|<работа>]] — <fork/branch + what's changed>Module note template (<module>.md)
# <module>
What this module is responsible for, in 2-3 sentences.
## Key files
- `path/to/file.py` — role. [GitHub](permalink)
- `ClassOrFunc` (`file.py:LINE`) — what it does.
## How it fits the run
Where this is called from (link [[architecture]]), inputs/outputs.
## Where to edit to change X
- ... → `file.py:LINE`Rules
- Never copy large code blocks. Cite
path:line+ GitHub permalink + a sentence. The notes are a map, not a mirror. - Keep each note focused; 200-400 lines max, split if larger.
- Pin permalinks to the analyzed commit/branch so line anchors stay valid; note the branch.
- Use Obsidian wikilinks between the overview and module notes.
- After ingesting, remind the user to add a
## Кодsection to the relevant project hub card (see [[code-library]]).
Does it work?
Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.
No reviews yet
People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.
- It worked
- Partly
- It didn't
Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.
Your trail
Files you open will collect here, so you can find them again.
Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.
Now do this for your own.
Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.

